Semantic Entity Labeling On Funsd

Métriques

F1

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
LayoutMask (large)	93.20	LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding
ERNIE-Layoutlarge	93.12	ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
LayoutMask (base)	92.91	LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding
GeoLayoutLM	92.86	GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
LayoutLMv3 Large	92.08	LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
RORE (GeoLayoutLM)	91.84	Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
StrucTexTv2 (large)	91.82	StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
XDoc1M	89.4	XDoc: Unified Pre-training for Cross-Format Document Understanding
StrucTexTv2 (small)	89.23	StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
LILT	88.41	LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
TPP (LayoutMask)	85.16	Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
LayoutLMv2LARGE	84.2	LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
DocTr	84	DocTr: Document Transformer for Structured Information Extraction in Documents
LayoutLMv2BASE	82.76	LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
Doc2Graph	82.25	Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks

0 of 15 row(s) selected.

Semantic Entity Labeling On Funsd | SOTA | HyperAI